EP3896702A1 - Cardiovascular assessment of patients suspected of having covid-19 - Google Patents
Cardiovascular assessment of patients suspected of having covid-19 Download PDFInfo
- Publication number
- EP3896702A1 EP3896702A1 EP21167781.0A EP21167781A EP3896702A1 EP 3896702 A1 EP3896702 A1 EP 3896702A1 EP 21167781 A EP21167781 A EP 21167781A EP 3896702 A1 EP3896702 A1 EP 3896702A1
- Authority
- EP
- European Patent Office
- Prior art keywords
- patient
- data
- cardiovascular
- assessment
- medical images
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000002526 effect on cardiovascular system Effects 0.000 title claims abstract description 98
- 208000025721 COVID-19 Diseases 0.000 title claims description 32
- 238000000034 method Methods 0.000 claims abstract description 45
- 208000019693 Lung disease Diseases 0.000 claims abstract description 36
- 238000010801 machine learning Methods 0.000 claims abstract description 35
- 208000024172 Cardiovascular disease Diseases 0.000 claims abstract description 17
- 238000003384 imaging method Methods 0.000 claims abstract description 17
- 230000006870 function Effects 0.000 claims description 36
- 238000012549 training Methods 0.000 claims description 25
- 238000004590 computer program Methods 0.000 claims description 16
- 238000013170 computed tomography imaging Methods 0.000 claims description 10
- 230000000747 cardiac effect Effects 0.000 claims description 9
- 206010035737 Pneumonia viral Diseases 0.000 claims description 4
- 239000002872 contrast media Substances 0.000 claims description 4
- 208000009421 viral pneumonia Diseases 0.000 claims description 4
- 238000005259 measurement Methods 0.000 claims description 3
- 230000001225 therapeutic effect Effects 0.000 claims 2
- 238000012544 monitoring process Methods 0.000 claims 1
- 238000013528 artificial neural network Methods 0.000 description 26
- 230000015654 memory Effects 0.000 description 16
- 238000011176 pooling Methods 0.000 description 16
- 239000011159 matrix material Substances 0.000 description 15
- 210000004072 lung Anatomy 0.000 description 14
- 238000013527 convolutional neural network Methods 0.000 description 11
- 238000011002 quantification Methods 0.000 description 9
- 238000002591 computed tomography Methods 0.000 description 8
- 206010035664 Pneumonia Diseases 0.000 description 6
- 230000008901 benefit Effects 0.000 description 6
- 238000013500 data storage Methods 0.000 description 6
- 208000024891 symptom Diseases 0.000 description 6
- OYPRJOBELJOOCE-UHFFFAOYSA-N Calcium Chemical compound [Ca] OYPRJOBELJOOCE-UHFFFAOYSA-N 0.000 description 5
- 238000013473 artificial intelligence Methods 0.000 description 5
- 229910052791 calcium Inorganic materials 0.000 description 5
- 239000011575 calcium Substances 0.000 description 5
- 210000000038 chest Anatomy 0.000 description 5
- 201000010099 disease Diseases 0.000 description 5
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 5
- 210000000709 aorta Anatomy 0.000 description 4
- 210000002216 heart Anatomy 0.000 description 4
- 238000007726 management method Methods 0.000 description 4
- 230000000007 visual effect Effects 0.000 description 4
- 201000003176 Severe Acute Respiratory Syndrome Diseases 0.000 description 3
- 230000004913 activation Effects 0.000 description 3
- 239000000090 biomarker Substances 0.000 description 3
- 230000036772 blood pressure Effects 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 3
- 208000015181 infectious disease Diseases 0.000 description 3
- 238000012546 transfer Methods 0.000 description 3
- 238000002604 ultrasonography Methods 0.000 description 3
- 201000001178 Bacterial Pneumonia Diseases 0.000 description 2
- 208000035473 Communicable disease Diseases 0.000 description 2
- 208000001528 Coronaviridae Infections Diseases 0.000 description 2
- 206010011224 Cough Diseases 0.000 description 2
- 206010013975 Dyspnoeas Diseases 0.000 description 2
- WQZGKKKJIJFFOK-GASJEMHNSA-N Glucose Natural products OC[C@H]1OC(O)[C@H](O)[C@@H](O)[C@@H]1O WQZGKKKJIJFFOK-GASJEMHNSA-N 0.000 description 2
- 208000013875 Heart injury Diseases 0.000 description 2
- 208000001572 Mycoplasma Pneumonia Diseases 0.000 description 2
- 201000008235 Mycoplasma pneumoniae pneumonia Diseases 0.000 description 2
- 206010037660 Pyrexia Diseases 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 2
- 230000009471 action Effects 0.000 description 2
- 239000008280 blood Substances 0.000 description 2
- 210000004369 blood Anatomy 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- HVYWMOMLDIMFJA-DPAQBDIFSA-N cholesterol Chemical compound C1C=C2C[C@@H](O)CC[C@]2(C)[C@@H]2[C@@H]1[C@@H]1CC[C@H]([C@H](C)CCCC(C)C)[C@@]1(C)CC2 HVYWMOMLDIMFJA-DPAQBDIFSA-N 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000000537 electroencephalography Methods 0.000 description 2
- 230000002538 fungal effect Effects 0.000 description 2
- 230000002068 genetic effect Effects 0.000 description 2
- 239000008103 glucose Substances 0.000 description 2
- 238000002595 magnetic resonance imaging Methods 0.000 description 2
- 230000001537 neural effect Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 210000001147 pulmonary artery Anatomy 0.000 description 2
- 230000000241 respiratory effect Effects 0.000 description 2
- 239000007787 solid Substances 0.000 description 2
- 238000013517 stratification Methods 0.000 description 2
- 230000035882 stress Effects 0.000 description 2
- 210000004243 sweat Anatomy 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000002792 vascular Effects 0.000 description 2
- 206010003598 Atelectasis Diseases 0.000 description 1
- 241000711573 Coronaviridae Species 0.000 description 1
- 206010020772 Hypertension Diseases 0.000 description 1
- 208000034486 Multi-organ failure Diseases 0.000 description 1
- 208000010718 Multiple Organ Failure Diseases 0.000 description 1
- 208000002151 Pleural effusion Diseases 0.000 description 1
- 208000007123 Pulmonary Atelectasis Diseases 0.000 description 1
- 208000027418 Wounds and injury Diseases 0.000 description 1
- 210000000577 adipose tissue Anatomy 0.000 description 1
- 210000003484 anatomy Anatomy 0.000 description 1
- 210000002376 aorta thoracic Anatomy 0.000 description 1
- 210000001765 aortic valve Anatomy 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 1
- 201000009267 bronchiectasis Diseases 0.000 description 1
- 210000005242 cardiac chamber Anatomy 0.000 description 1
- 238000013184 cardiac magnetic resonance imaging Methods 0.000 description 1
- 230000002612 cardiopulmonary effect Effects 0.000 description 1
- 210000000748 cardiovascular system Anatomy 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 235000012000 cholesterol Nutrition 0.000 description 1
- 230000003920 cognitive function Effects 0.000 description 1
- 238000007596 consolidation process Methods 0.000 description 1
- 210000004351 coronary vessel Anatomy 0.000 description 1
- 230000001186 cumulative effect Effects 0.000 description 1
- 230000006378 damage Effects 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 206010012601 diabetes mellitus Diseases 0.000 description 1
- 230000009429 distress Effects 0.000 description 1
- 238000002592 echocardiography Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 239000005337 ground glass Substances 0.000 description 1
- 230000008595 infiltration Effects 0.000 description 1
- 238000001764 infiltration Methods 0.000 description 1
- 208000014674 injury Diseases 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000003064 k means clustering Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 208000029744 multiple organ dysfunction syndrome Diseases 0.000 description 1
- 230000002107 myocardial effect Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 229910052760 oxygen Inorganic materials 0.000 description 1
- 239000001301 oxygen Substances 0.000 description 1
- 230000010412 perfusion Effects 0.000 description 1
- 210000003516 pericardium Anatomy 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000035479 physiological effects, processes and functions Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000002787 reinforcement Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 238000002560 therapeutic procedure Methods 0.000 description 1
- 230000008719 thickening Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
- A61B5/0205—Simultaneously evaluating both cardiovascular conditions and different types of body conditions, e.g. heart and respiratory condition
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/48—Other medical applications
- A61B5/4842—Monitoring progression or stage of a disease
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
- G16H10/60—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/50—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for simulation or modelling of medical disorders
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/80—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for detecting, monitoring or modelling epidemics or pandemics, e.g. flu
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10072—Tomographic images
- G06T2207/10081—Computed x-ray tomography [CT]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30048—Heart; Cardiac
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30061—Lung
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30101—Blood vessel; Artery; Vein; Vascular
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
Definitions
- the present invention relates generally to a cardiovascular assessment, and in particular to the cardiovascular assessment of patients confirmed as having or suspected of having COVID-19 (coronavirus disease 2019) for patient management.
- COVID-19 coronavirus disease 2019
- SARS-Cov2 severe-acute respiratory symptom coronavirus 2
- Common symptoms of COVID-19 include fever, cough, and difficulty breathing.
- patients infected with COVID-19 experience mild to moderate symptoms that do not require hospitalization.
- COVID-19 can cause pneumonia, severe acute respiratory syndrome, multiple organ failure, and death.
- systems and methods for assessing cardiovascular disease of a patient are provided.
- Patient data of the patient is received.
- the patient data may include one or more input medical images of a chest of the patient, results of an assessment of a lung disease performed based on the one or more input medical images, demographic and clinical data of the patient, and cardiovascular imaging exams of the patient.
- One or more cardiovascular risk scores are computed for the patient based on the patient data using a trained machine learning based network.
- the patient may be managed based on the one or more cardiovascular risk scores.
- the lung disease may be COVID-19 (coronavirus disease 2019) or another viral pneumonia.
- the one or more input medical images are acquired without a contrast agent and without cardiac gating.
- the one or more risk scores is a metric representing an assessment of a cardiovascular disease and the assessment of the lung disease.
- the patient data includes sensor data of physiological measurements of the patient.
- the sensor data may be continuously received and the patient may be monitored based on the continuously received sensor data and the cardiovascular assessment.
- the present invention generally relates to methods and systems for the cardiovascular assessment of patients confirmed as having or suspected of having COVID-19 (coronavirus disease 2019). Embodiments of the present invention are described herein to give a visual understanding of such methods and systems.
- a digital image is often composed of digital representations of one or more objects (or shapes).
- the digital representation of an object is often described herein in terms of identifying and manipulating the objects.
- Such manipulations are virtual manipulations accomplished in the memory or other circuitry/hardware of a computer system. Accordingly, is to be understood that embodiments of the present invention may be performed within a computer system using data stored within the computer system.
- COVID-19 is an infectious disease that typically presents such respiratory symptoms as fever, cough, and difficulty breathing. Patients with COVID-19 that also have underlying cardiovascular disease have been found to exhibit more severe symptoms of COVID-19 and have worse patient outcomes (including death). Typically, patients suspected of having COVID-19 receive CT (computed tomography) imaging of the chest in order to assess the lungs. The CT imaging is primarily performed for the purpose of assessing the lungs and, therefore, the CT imaging is performed without contrast agent and without cardiac gating, resulting in relatively lower image quality of cardiovascular structures as compared to CT imaging typically used to assess cardiovascular disease. Embodiments described herein provide for a machine learning based system for the cardiovascular assessment of a patient using such CT imaging. Advantageously, the cardiovascular assessment for patients confirmed as having or suspected of having COVID-19 in accordance with embodiments described herein allows for improved patient management decisions and patient stratification, enabling better use of clinical resources and improved patient outcomes.
- embodiments described herein are described with respect to the cardiovascular assessment of patients confirmed as having or suspected of having COVID-19, such embodiments are not so limited. Embodiments may be applied for the cardiovascular assessment of patients confirmed as having or suspected of having any lung disease (e.g., other types of viral pneumonia (e.g., SARS (severe acute respiratory syndrome), MERS (Middle East respiratory syndrome), etc.), bacterial pneumonia, fungal pneumonia, mycoplasma pneumonia, and other types of pneumonia and other types of diseases).
- lung disease e.g., other types of viral pneumonia (e.g., SARS (severe acute respiratory syndrome), MERS (Middle East respiratory syndrome), etc.
- bacterial pneumonia e.g., fungal pneumonia, mycoplasma pneumonia, and other types of pneumonia and other types of diseases.
- Figure 1 shows a framework 100 for cardiovascular assessment of a patient confirmed as having or suspected of having a lung disease, in accordance with one or more embodiments.
- Figure 2 shows a method 200 for cardiovascular assessment of a patient confirmed as having or suspected of having a lung disease, in accordance with one or more embodiments.
- Figure 1 and Figure 2 will be described together.
- the steps of method 200 may be performed by one or more computing devices, such as, e.g., computer 502 of Figure 5 .
- patient data of a patient is received.
- the patient may be confirmed as having or suspected of having a lung disease.
- the lung disease is COVID-19.
- the lung disease may include any disease associated with the lungs of the patient, such as, e.g., other types of viral pneumonia (e.g., SARS (severe acute respiratory syndrome), MERS (Middle East respiratory syndrome), etc.), bacterial pneumonia, fungal pneumonia, mycoplasma pneumonia, and other types of pneumonia and other types of diseases.
- SARS severe acute respiratory syndrome
- MERS Middle East respiratory syndrome
- the patient data includes one or more input medical images of the chest (including the lungs and the heart) of the patient.
- the input medical images may depict abnormality patterns associated with the lung disease.
- the input medical images may show opacities such as, e.g., GGO (ground glass opacity), consolidation, crazy-paving pattern, atelectasis, interlobular septal thickening, pleural effusions, bronchiectasis, etc.
- the input medical images are CT input medical images.
- the input medical images may be chest CT image 102 in framework 100 of Figure 1 .
- the input medical images may be of any suitable modality, such as, e.g., MRI (magnetic resonance imaging), US (ultrasound), x-ray, or any other modality or combination of modalities.
- the input medical images may comprise one or more 2D images or 3D volumes.
- the input medical images may be received directly from an image acquisition device, such as, e.g., a CT scanner, as the input medical images are acquired, or can be received by loading previously acquired input medical images from a storage or memory of a computer system or receiving the input medical images from a remote computer system.
- the input medical images are acquired during a clinical workflow for diagnosing or treating the patient for the lung disease.
- the input medical images may be acquired with or without using a contrast agent, without cardiac gating, with a relatively lower spatial resolution as compared to typical cardiac CT imaging, and with low dose CT imaging. While such images are suitable for assessment of the lung disease, the images are relatively lower quality images as compared to typical medical images acquired for the purpose of assessing cardiovascular disease.
- the patient data includes results of an assessment of the lung disease performed based on the input medical images.
- the results of the assessment of the lung disease may be results of assessment of lung disease 104 in framework 100 of Figure 1 .
- the assessment of the lung disease is a quantitative assessment of the lung disease performed on the input medical images using a machine learning based network.
- the results of the quantitative assessment may include metrics quantifying the lung disease. For example, where the lung disease is COVID-19, the quantitative assessment may quantify abnormality patterns associated with COVID-19.
- Exemplary metrics include a PO (percent of opacity) metric calculated as the total percent volume of the lungs that is affected by the disease and a LSS (lung severity score) metric calculated as a cumulative measure of the extent of lung involvement in the disease across each lobe of the lungs. Other metrics are also contemplated.
- the assessment of the lung disease is a qualitative assessment of the lung disease performed by a clinician or other user.
- the patient data includes results of cardiovascular imaging exams.
- the results of cardiovascular imaging exams may be results of cardiovascular imaging exams 106 in framework 100 of Figure 1 .
- the cardiovascular imaging exam may be based on any suitable modality or combination of modalities.
- Exemplary cardiovascular imaging exams include echocardiography, vascular ultrasound, cardiac MRI, cardiac CT, cardiac PET, or any other cardiovascular imaging exam.
- the patient data includes demographic and clinical data of the patient.
- the demographic and clinical data may be demographic and clinical data 108 in framework 100 of Figure 1 .
- the demographic and clinical data may include any data relating to the patient, such as, e.g., age, gender, clinical history, genetic and family history, risk factors (e.g., hypertension, diabetes, etc.), lab values, etc.
- the demographic and clinical data includes sensor data of physiological measurements of the patient.
- the sensor data may include, e.g., ECG (electrocardiogram) data, EEG (electroencephalography) data, blood pressure data, O2 (oxygen) saturation, blood pH, glucose levels, etc.
- ECG electrocardiogram
- EEG electroencephalography
- O2 oxygen saturation
- the sensor data may be acquired from sensors and medical equipment, including non-medical grade sensor devices.
- Exemplary sensors include a blood pressure meter, heart rate sensor, ECG monitor, pulse oximeter, O2 saturation sensor, sweat sensors, smart watches and wearable sensors, etc.
- the sensor data may be continuously acquired or periodically acquired at predetermined intervals.
- one or more cardiovascular risk scores are computed for the patient based on the patient data using a trained machine learning based network.
- the cardiovascular risk scores represent an assessment of risk or injury relating to the heart or vessels of the patient.
- cardiovascular risk scores 112 are computed using automated AI (artificial intelligence)-based cardiovascular disease assessment system 110 in framework 100 of Figure 1 .
- the trained machine learning based network is a deep learning based network, however any other suitable machine learning based network may be employed.
- the cardiovascular risk scores are based on multiple cardiovascular findings independently determined by different respective machine learning networks.
- the trained machine learning based network is trained to compute that cardiovascular risk scores during a prior offline or training stage using a training dataset and, once trained, applied at step 204 during an online or inference stage.
- the cardiovascular risk scores of the patient represents a quantification of cardiovascular risk of the patient.
- the cardiovascular risk scores may be a quantification of an amount of calcium in the coronary arteries (total calcium or calcium in each branch), a quantification of a calcium load in the aorta (e.g., the aortic root, thoracic aorta, or aortic valve leaflets), or a quantification of the size of the aorta and pulmonary artery.
- the cardiovascular risk scores may be a quantification of epicardial fat, paracardial fat, or epicardial adipose tissue.
- the cardiovascular risk scores may be a quantification of myocardial fat (infiltration).
- a cardiovascular assessment of the patient is also determined based on the patient data using the trained machine learning based network.
- the cardiovascular assessment of the patient may comprise an automatic extraction of various anatomical structures (e.g., cardiovascular structures such as pericardium, heart chambers, aorta, pulmonary artery, etc.) from the input medical images.
- the cardiovascular assessment of the patient comprises imaging biomarkers identified in the input medical images.
- the cardiovascular assessment of the patient comprises cardiovascular-specific imaging features extracted from the input medical images by the trained machine learning based network.
- the extracted imaging features may be combined with other patient data for a more comprehensive assessment.
- the extracted imaging features may be combined with cardiovascular disease imaging biomarkers obtained via ultrasound from other vascular territories, such as, e.g., carotids, aorta, and the ileo-femoral region.
- the cardiovascular assessment of the patient comprises a recommended course of action for clinical decision support.
- the recommended course of action may be a suggested duration for following up with the patient.
- the cardiovascular risk scores for the patient comprises a combination metric representing an assessment of the cardiovascular disease of the patient, as well as the lung disease of the patient.
- the combination metric may be computed based on the imaging biomarkers in the input medical image combined with other patient data of the patient.
- the combination metric is an assessment of the overall cardiopulmonary system, including the lungs and the heart of the patient, representing the extent, severity, and risk of both the lung disease and cardiovascular disease.
- the combination metric may be the assessment of the lungs normalized in the context of the cardiovascular assessment (e.g., the quantification of the cardiovascular risk).
- the combination metric may represent the cardiovascular assessment (e.g., the quantification of the cardiovascular risk) quantified in the context of the assessment of the lung disease.
- the quantification of the cardiovascular risk may be normalized with respect to an amount of infection in the lungs or a lung perfusion.
- Other metrics may also be employed that do not directly relate to cardiovascular disease.
- the cardiovascular risk scores and/or the cardiovascular assessment of the patient are output.
- the cardiovascular risk scores and/or the cardiovascular assessment can be output by displaying the cardiovascular risk scores and/or the cardiovascular assessment on a display device of a computer system, storing the cardiovascular risk scores and/or the cardiovascular assessment on a memory or storage of a computer system, or by transmitting the cardiovascular risk scores and/or the cardiovascular assessment to a remote computer system.
- the cardiovascular risk scores and/or the cardiovascular assessment may be output as a visual report highlighting various sources of cardiac risk (e.g., coronary calcium, epicardial fat, enlargement of great vessels, etc.).
- the cardiovascular risk scores and/or the cardiovascular assessment for the patient may be displayed in the visual report along with cardiovascular risk scores and/or the cardiovascular assessments for other patients, where the patients are sorted (on demand or automatically) within the visual report based on cardiovascular risk.
- a clinician (or other user) may be receive a notification (e.g., an email, text or chat message, or an application based notification) indicating that the cardiovascular risk scores and/or the cardiovascular assessment are complete.
- the clinical may interact with (e.g., select) the notification to view the cardiovascular risk scores and/or the cardiovascular assessment.
- the cardiovascular risk scores and/or the cardiovascular assessment may be utilized by a clinical for patient management.
- the clinician may order additional tests, change therapies, manage clinical resources, etc. based on the cardiovascular risk scores and/or the cardiovascular assessment.
- the patient data may be used in the context of the cardiovascular risk scores and/or the cardiovascular assessment to identify signs of cardiac distress.
- the patient data may be sensor data from one or more sensors, such as an ECG monitor, blood pressure, sensor, O2 saturation sensor, smart watch, sweat sensor, laboratory testing data (e.g., troponin levels, blood glucose levels, cholesterol, etc.), or any other sensor.
- the sensor data in combination with patient data, may be continuously received and used to build a continuously evolving model of the physiology of the patient.
- the model may be used to monitor the patient for sudden changes indicative of cardiac injury or stress based on the continuously received sensor data and the cardiovascular risk scores and/or the cardiovascular assessment. Where such indications of cardiac injury or stress are detected, a notification may be transmitted to the clinician for further assessment of the patient.
- the cardiovascular risk scores and/or the cardiovascular assessment of a patient in accordance with embodiments described herein assist clinicians in patient management decisions and patient stratification.
- the cardiovascular risk scores and/or the cardiovascular assessment are determined using patient data acquired in the clinical workflow for diagnosing or treating the lung disease and therefore requires minimal time from clinicians, which is particularly important for clinicians treating patients with COVID-19. Further, the cardiovascular risk scores and/or the cardiovascular assessment is determined based on a combination of various patient data and thus, the accuracy of specific patient data is not critical for determining the cardiovascular assessment.
- Embodiments described herein are described with respect to the claimed systems as well as with respect to the claimed methods.
- Features, advantages or alternative embodiments herein can be assigned to the other claimed objects and vice versa.
- claims for the systems can be improved with features described or claimed in the context of the methods.
- the functional features of the method are embodied by objective units of the providing system.
- embodiments described herein are described with respect to methods and systems for cardiovascular assessment of patients suspected of having COVID-19 using a trained machine learning based network, as well as with respect to methods and systems for training a machine learning based network for cardiovascular assessment of patients suspected of having COVID-19.
- Features, advantages or alternative embodiments herein can be assigned to the other claimed objects and vice versa.
- claims for methods and systems for training a machine learning based generator network can be improved with features described or claimed in context of the methods and systems for utilizing a trained machine learning based generator network, and vice versa.
- the trained machine learning based network of the methods and systems for cardiovascular assessment of patients suspected of having COVID-19 can be adapted by the methods and systems for training the machine learning based network for cardiovascular assessment of patients suspected of having COVID-19.
- the input data of the trained machine learning based network can comprise advantageous features and embodiments of the training input data, and vice versa.
- the output data of the trained machine learning based network can comprise advantageous features and embodiments of the output training data, and vice versa.
- a trained machine learning based network mimics cognitive functions that humans associate with other human minds.
- the trained machine learning based network is able to adapt to new circumstances and to detect and extrapolate patterns.
- parameters of a machine learning based network can be adapted by means of training.
- supervised training, semi-supervised training, unsupervised training, reinforcement learning and/or active learning can be used.
- representation learning an alternative term is "feature learning”
- the parameters of the trained machine learning based network can be adapted iteratively by several steps of training.
- a trained machine learning based network can comprise a neural network, a support vector machine, a decision tree, and/or a Bayesian network, and/or the trained machine learning based network can be based on k-means clustering, Q-learning, genetic algorithms, and/or association rules.
- a neural network can be a deep neural network, a convolutional neural network, or a convolutional deep neural network.
- a neural network can be an adversarial network, a deep adversarial network and/or a generative adversarial network.
- Figure 3 shows an embodiment of an artificial neural network 300, in accordance with one or more embodiments.
- artificial neural network alternatives terms for “artificial neural network” are “neural network”, “artificial neural net” or “neural net”.
- Machine learning networks described herein such as, e.g., the automated AI-based cardiovascular disease assessment system 110 of Figure 1 and the machine learning based network applied at step 204 of Figure 2 , may be implemented using artificial neural network 300.
- the artificial neural network 300 comprises nodes 302-322 and edges 332, 334, ..., 336, wherein each edge 332, 334, ..., 336 is a directed connection from a first node 302-322 to a second node 302-322.
- the first node 302-322 and the second node 302-322 are different nodes 302-322, it is also possible that the first node 302-322 and the second node 302-322 are identical.
- the edge 332 is a directed connection from the node 302 to the node 306, and the edge 334 is a directed connection from the node 304 to the node 306.
- An edge 332, 334, ..., 336 from a first node 302-322 to a second node 302-322 is also denoted as "ingoing edge” for the second node 302-322 and as “outgoing edge” for the first node 302-322.
- the nodes 302-322 of the artificial neural network 300 can be arranged in layers 324-330, wherein the layers can comprise an intrinsic order introduced by the edges 332, 334, ..., 336 between the nodes 302-322.
- edges 332, 334, ..., 336 can exist only between neighboring layers of nodes.
- the number of hidden layers 326, 328 can be chosen arbitrarily.
- the number of nodes 302 and 304 within the input layer 324 usually relates to the number of input values of the neural network 300
- the number of nodes 322 within the output layer 330 usually relates to the number of output values of the neural network 300.
- a (real) number can be assigned as a value to every node 302-322 of the neural network 300.
- x (n) i denotes the value of the i-th node 302-322 of the n-th layer 324-330.
- the values of the nodes 302-322 of the input layer 324 are equivalent to the input values of the neural network 300
- the value of the node 322 of the output layer 330 is equivalent to the output value of the neural network 300.
- each edge 332, 334, ..., 336 can comprise a weight being a real number, in particular, the weight is a real number within the interval [-1, 1] or within the interval [0, 1].
- w (m,n) i,j denotes the weight of the edge between the i-th node 302-322 of the m-th layer 324-330 and the j-th node 302-322 of the n-th layer 324-330. Furthermore, the abbreviation w (n) i,j is defined for the weight w (n,n+1) i,j .
- the input values are propagated through the neural network.
- the function f is a transfer function (another term is "activation function").
- transfer functions are step functions, sigmoid function (e.g. the logistic function, the generalized logistic function, the hyperbolic tangent, the Arctangent function, the error function, the smoothstep function) or rectifier functions
- sigmoid function e.g. the logistic function, the generalized logistic function, the hyperbolic tangent, the Arctangent function, the error function, the smoothstep function
- rectifier functions e.g. the logistic function, the generalized logistic function, the hyperbolic tangent, the Arctangent function, the error function, the smoothstep function
- the transfer function is mainly used for normalization purposes.
- the values are propagated layer-wise through the neural network, wherein values of the input layer 324 are given by the input of the neural network 300, wherein values of the first hidden layer 326 can be calculated based on the values of the input layer 324 of the neural network, wherein values of the second hidden layer 328 can be calculated based in the values of the first hidden layer 326, etc.
- training data comprises training input data and training output data (denoted as t i ).
- training output data denoted as t i .
- the neural network 300 is applied to the training input data to generate calculated output data.
- the training data and the calculated output data comprise a number of values, said number being equal with the number of nodes of the output layer.
- a comparison between the calculated output data and the training data is used to recursively adapt the weights within the neural network 300 (backpropagation algorithm).
- Y is a learning rate
- FIG 4 shows a convolutional neural network 400, in accordance with one or more embodiments.
- Machine learning networks described herein such as, e.g., the automated AI-based cardiovascular disease assessment system 110 of Figure 1 and the machine learning based network applied at step 204 of Figure 2 , may be implemented using convolutional neural network 400.
- the convolutional neural network comprises 400 an input layer 402, a convolutional layer 404, a pooling layer 406, a fully connected layer 408, and an output layer 410.
- the convolutional neural network 400 can comprise several convolutional layers 404, several pooling layers 406, and several fully connected layers 408, as well as other types of layers.
- the order of the layers can be chosen arbitrarily, usually fully connected layers 408 are used as the last layers before the output layer 410.
- the nodes 412-420 of one layer 402-410 can be considered to be arranged as a d-dimensional matrix or as a d-dimensional image.
- the value of the node 412-420 indexed with i and j in the n-th layer 402-410 can be denoted as x (n )[ i,j ].
- the arrangement of the nodes 412-420 of one layer 402-410 does not have an effect on the calculations executed within the convolutional neural network 400 as such, since these are given solely by the structure and the weights of the edges.
- a convolutional layer 404 is characterized by the structure and the weights of the incoming edges forming a convolution operation based on a certain number of kernels.
- the k-th kernel K k is a d-dimensional matrix (in this embodiment a two-dimensional matrix), which is usually small compared to the number of nodes 412-418 (e.g. a 3x3 matrix, or a 5x5 matrix).
- a kernel being a 3x3 matrix, there are only 9 independent weights (each entry of the kernel matrix corresponding to one independent weight), irrespectively of the number of nodes 412-420 in the respective layer 402-410.
- the number of nodes 414 in the convolutional layer is equivalent to the number of nodes 412 in the preceding layer 402 multiplied with the number of kernels.
- nodes 412 of the preceding layer 402 are arranged as a d-dimensional matrix, using a plurality of kernels can be interpreted as adding a further dimension (denoted as "depth” dimension), so that the nodes 414 of the convolutional layer 414 are arranged as a (d+1)-dimensional matrix.
- nodes 412 of the preceding layer 402 are already arranged as a (d+1)-dimensional matrix comprising a depth dimension, using a plurality of kernels can be interpreted as expanding along the depth dimension, so that the nodes 414 of the convolutional layer 404 are arranged also as a (d+1)-dimensional matrix, wherein the size of the (d+1)-dimensional matrix with respect to the depth dimension is by a factor of the number of kernels larger than in the preceding layer 402.
- convolutional layers 404 The advantage of using convolutional layers 404 is that spatially local correlation of the input data can exploited by enforcing a local connectivity pattern between nodes of adjacent layers, in particular by each node being connected to only a small region of the nodes of the preceding layer.
- the input layer 402 comprises 36 nodes 412, arranged as a two-dimensional 6x6 matrix.
- the convolutional layer 404 comprises 72 nodes 414, arranged as two two-dimensional 6x6 matrices, each of the two matrices being the result of a convolution of the values of the input layer with a kernel. Equivalently, the nodes 414 of the convolutional layer 404 can be interpreted as arranges as a three-dimensional 6x6x2 matrix, wherein the last dimension is the depth dimension.
- a pooling layer 406 can be characterized by the structure and the weights of the incoming edges and the activation function of its nodes 416 forming a pooling operation based on a non-linear pooling function f.
- the number of nodes 414, 416 can be reduced, by replacing a number d1 ⁇ d2 of neighboring nodes 414 in the preceding layer 404 with a single node 416 being calculated as a function of the values of said number of neighboring nodes in the pooling layer.
- the pooling function f can be the max-function, the average or the L2-Norm.
- the weights of the incoming edges are fixed and are not modified by training.
- the advantage of using a pooling layer 406 is that the number of nodes 414, 416 and the number of parameters is reduced. This leads to the amount of computation in the network being reduced and to a control of overfitting.
- the pooling layer 406 is a max-pooling, replacing four neighboring nodes with only one node, the value being the maximum of the values of the four neighboring nodes.
- the max-pooling is applied to each d-dimensional matrix of the previous layer; in this embodiment, the max-pooling is applied to each of the two two-dimensional matrices, reducing the number of nodes from 72 to 18.
- a fully-connected layer 408 can be characterized by the fact that a majority, in particular, all edges between nodes 416 of the previous layer 406 and the nodes 418 of the fully-connected layer 408 are present, and wherein the weight of each of the edges can be adjusted individually.
- the nodes 416 of the preceding layer 406 of the fully-connected layer 408 are displayed both as two-dimensional matrices, and additionally as non-related nodes (indicated as a line of nodes, wherein the number of nodes was reduced for a better presentability).
- the number of nodes 418 in the fully connected layer 408 is equal to the number of nodes 416 in the preceding layer 406.
- the number of nodes 416, 418 can differ.
- the values of the nodes 420 of the output layer 410 are determined by applying the Softmax function onto the values of the nodes 418 of the preceding layer 408.
- the Softmax function By applying the Softmax function, the sum the values of all nodes 420 of the output layer 410 is 1, and all values of all nodes 420 of the output layer are real numbers between 0 and 1.
- a convolutional neural network 400 can also comprise a ReLU (rectified linear units) layer.
- the number of nodes and the structure of the nodes contained in a ReLU layer is equivalent to the number of nodes and the structure of the nodes contained in the preceding layer.
- convolutional neural networks 400 can be trained based on the backpropagation algorithm.
- methods of regularization can be used, e.g. dropout of nodes 412-420, stochastic pooling, use of artificial data, weight decay based on the L1 or the L2 norm, or max norm constraints.
- Systems, apparatuses, and methods described herein may be implemented using digital circuitry, or using one or more computers using well-known computer processors, memory units, storage devices, computer software, and other components.
- a computer includes a processor for executing instructions and one or more memories for storing instructions and data.
- a computer may also include, or be coupled to, one or more mass storage devices, such as one or more magnetic disks, internal hard disks and removable disks, magneto-optical disks, optical disks, etc.
- Systems, apparatus, and methods described herein may be implemented using computers operating in a client-server relationship.
- the client computers are located remotely from the server computer and interact via a network.
- the client-server relationship may be defined and controlled by computer programs running on the respective client and server computers.
- Systems, apparatus, and methods described herein may be implemented within a network-based cloud computing system.
- a server or another processor that is connected to a network communicates with one or more client computers via a network.
- a client computer may communicate with the server via a network browser application residing and operating on the client computer, for example.
- a client computer may store data on the server and access the data via the network.
- a client computer may transmit requests for data, or requests for online services, to the server via the network.
- the server may perform requested services and provide data to the client computer(s).
- the server may also transmit data adapted to cause a client computer to perform a specified function, e.g., to perform a calculation, to display specified data on a screen, etc.
- the server may transmit a request adapted to cause a client computer to perform one or more of the steps or functions of the methods and workflows described herein, including one or more of the steps or functions of Figures 1-2 .
- Certain steps or functions of the methods and workflows described herein, including one or more of the steps or functions of Figures 1-2 may be performed by a server or by another processor in a network-based cloud-computing system.
- Certain steps or functions of the methods and workflows described herein, including one or more of the steps of Figures 1-2 may be performed by a client computer in a network-based cloud computing system.
- the steps or functions of the methods and workflows described herein, including one or more of the steps of Figures 1-2 may be performed by a server and/or by a client computer in a network-based cloud computing system, in any combination.
- Systems, apparatus, and methods described herein may be implemented using a computer program product tangibly embodied in an information carrier, e.g., in a non-transitory machine-readable storage device, for execution by a programmable processor; and the method and workflow steps described herein, including one or more of the steps or functions of Figures 1-2 , may be implemented using one or more computer programs that are executable by such a processor.
- a computer program is a set of computer program instructions that can be used, directly or indirectly, in a computer to perform a certain activity or bring about a certain result.
- a computer program can be written in any form of programming language, including compiled or interpreted languages, and it can be deployed in any form, including as a stand-alone program or as a module, component, subroutine, or other unit suitable for use in a computing environment.
- Computer 502 includes a processor 504 operatively coupled to a data storage device 512 and a memory 510.
- Processor 504 controls the overall operation of computer 502 by executing computer program instructions that define such operations.
- the computer program instructions may be stored in data storage device 512, or other computer readable medium, and loaded into memory 510 when execution of the computer program instructions is desired.
- the method and workflow steps or functions of Figures 1-2 can be defined by the computer program instructions stored in memory 510 and/or data storage device 512 and controlled by processor 504 executing the computer program instructions.
- the computer program instructions can be implemented as computer executable code programmed by one skilled in the art to perform the method and workflow steps or functions of Figures 1-2 . Accordingly, by executing the computer program instructions, the processor 504 executes the method and workflow steps or functions of Figures 1-2 .
- Computer 502 may also include one or more network interfaces 506 for communicating with other devices via a network.
- Computer 502 may also include one or more input/output devices 508 that enable user interaction with computer 502 (e.g., display, keyboard, mouse, speakers, buttons, etc.).
- Processor 504 may include both general and special purpose microprocessors, and may be the sole processor or one of multiple processors of computer 502.
- Processor 504 may include one or more central processing units (CPUs), for example.
- Processor 504, data storage device 512, and/or memory 510 may include, be supplemented by, or incorporated in, one or more application-specific integrated circuits (ASICs) and/or one or more field programmable gate arrays (FPGAs).
- ASICs application-specific integrated circuits
- FPGAs field programmable gate arrays
- Data storage device 512 and memory 510 each include a tangible non-transitory computer readable storage medium.
- Data storage device 512, and memory 510 may each include high-speed random access memory, such as dynamic random access memory (DRAM), static random access memory (SRAM), double data rate synchronous dynamic random access memory (DDR RAM), or other random access solid state memory devices, and may include non-volatile memory, such as one or more magnetic disk storage devices such as internal hard disks and removable disks, magneto-optical disk storage devices, optical disk storage devices, flash memory devices, semiconductor memory devices, such as erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM), digital versatile disc read-only memory (DVD-ROM) disks, or other non-volatile solid state storage devices.
- DRAM dynamic random access memory
- SRAM static random access memory
- DDR RAM double data rate synchronous dynamic random access memory
- non-volatile memory such as one
- Input/output devices 508 may include peripherals, such as a printer, scanner, display screen, etc.
- input/output devices 508 may include a display device such as a cathode ray tube (CRT) or liquid crystal display (LCD) monitor for displaying information to the user, a keyboard, and a pointing device such as a mouse or a trackball by which the user can provide input to computer 502.
- display device such as a cathode ray tube (CRT) or liquid crystal display (LCD) monitor for displaying information to the user
- keyboard a keyboard
- pointing device such as a mouse or a trackball by which the user can provide input to computer 502.
- An image acquisition device 514 can be connected to the computer 502 to input image data (e.g., medical images) to the computer 502. It is possible to implement the image acquisition device 514 and the computer 502 as one device. It is also possible that the image acquisition device 514 and the computer 502 communicate wirelessly through a network. In a possible embodiment, the computer 502 can be located remotely with respect to the image acquisition device 514.
- image data e.g., medical images
- Any or all of the systems and apparatus discussed herein, including automated AI-based cardiovascular disease assessment system 110 of Figure 1 , the machine learning based network applied at step 204 of Figure 2 , the artificial neural network 300 of Figure 3 , and the convolutional neural network 400 of Figure 4 , may be implemented using one or more computers such as computer 502.
Landscapes
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Public Health (AREA)
- Medical Informatics (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Pathology (AREA)
- Primary Health Care (AREA)
- Epidemiology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- General Physics & Mathematics (AREA)
- Animal Behavior & Ethology (AREA)
- Physiology (AREA)
- Cardiology (AREA)
- Heart & Thoracic Surgery (AREA)
- Surgery (AREA)
- Veterinary Medicine (AREA)
- Mathematical Physics (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Computational Linguistics (AREA)
- Pulmonology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Quality & Reliability (AREA)
- Radiology & Medical Imaging (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
Description
- This application claims the benefit of
U.S. Provisional Application No. 63/009,517, filed April 14, 2020 - The present invention relates generally to a cardiovascular assessment, and in particular to the cardiovascular assessment of patients confirmed as having or suspected of having COVID-19 (coronavirus disease 2019) for patient management.
- COVID-19 (coronavirus disease 2019) is an infectious disease caused by the severe-acute respiratory symptom coronavirus 2 (SARS-Cov2). Common symptoms of COVID-19 include fever, cough, and difficulty breathing. In the majority of cases, patients infected with COVID-19 experience mild to moderate symptoms that do not require hospitalization. However, in severe cases, COVID-19 can cause pneumonia, severe acute respiratory syndrome, multiple organ failure, and death.
- Studies have shown that patients infected with COVID-19 that also have underlying cardiovascular disease are at a higher risk for experiencing severe symptoms of COVID-19. Typically, patients suspected of being infected with COVID-19 receive CT (computed tomography) imaging of the chest for the purpose of assessing the lungs for pneumonia and other pulmonary diseases. However, existing automatic techniques are not able to assess the cardiovascular system of a patient based on such CT imaging, since the CT imaging is primarily performed to assess the lungs of the patient and is not optimized for assessing cardiovascular disease of the patient.
- In accordance with one or more embodiments, systems and methods for assessing cardiovascular disease of a patient are provided. Patient data of the patient is received. The patient data may include one or more input medical images of a chest of the patient, results of an assessment of a lung disease performed based on the one or more input medical images, demographic and clinical data of the patient, and cardiovascular imaging exams of the patient. One or more cardiovascular risk scores are computed for the patient based on the patient data using a trained machine learning based network. The patient may be managed based on the one or more cardiovascular risk scores.
- In one embodiment, the lung disease may be COVID-19 (coronavirus disease 2019) or another viral pneumonia.
- In one embodiment, the one or more input medical images are acquired without a contrast agent and without cardiac gating.
- In one embodiment, the one or more risk scores is a metric representing an assessment of a cardiovascular disease and the assessment of the lung disease.
- In one embodiment, the patient data includes sensor data of physiological measurements of the patient. The sensor data may be continuously received and the patient may be monitored based on the continuously received sensor data and the cardiovascular assessment.
- These and other advantages of the invention will be apparent to those of ordinary skill in the art by reference to the following detailed description and the accompanying drawings.
-
-
Figure 1 shows framework for cardiovascular assessment of a patient confirmed as having or suspected of having a lung disease, in accordance with one or more embodiments; -
Figure 2 shows a method for cardiovascular assessment of a patient confirmed as having or suspected of having a lung disease, in accordance with one or more embodiments; -
Figure 3 shows an exemplary artificial neural network that may be used to implement one or more embodiments described herein; -
Figure 4 shows a convolutional neural network that may be used to implement one or more embodiments described herein; and -
Figure 5 shows a high-level block diagram of a computer that may be used to implement one or more embodiments described herein. - The present invention generally relates to methods and systems for the cardiovascular assessment of patients confirmed as having or suspected of having COVID-19 (coronavirus disease 2019). Embodiments of the present invention are described herein to give a visual understanding of such methods and systems. A digital image is often composed of digital representations of one or more objects (or shapes). The digital representation of an object is often described herein in terms of identifying and manipulating the objects. Such manipulations are virtual manipulations accomplished in the memory or other circuitry/hardware of a computer system. Accordingly, is to be understood that embodiments of the present invention may be performed within a computer system using data stored within the computer system.
- COVID-19 is an infectious disease that typically presents such respiratory symptoms as fever, cough, and difficulty breathing. Patients with COVID-19 that also have underlying cardiovascular disease have been found to exhibit more severe symptoms of COVID-19 and have worse patient outcomes (including death). Typically, patients suspected of having COVID-19 receive CT (computed tomography) imaging of the chest in order to assess the lungs. The CT imaging is primarily performed for the purpose of assessing the lungs and, therefore, the CT imaging is performed without contrast agent and without cardiac gating, resulting in relatively lower image quality of cardiovascular structures as compared to CT imaging typically used to assess cardiovascular disease. Embodiments described herein provide for a machine learning based system for the cardiovascular assessment of a patient using such CT imaging. Advantageously, the cardiovascular assessment for patients confirmed as having or suspected of having COVID-19 in accordance with embodiments described herein allows for improved patient management decisions and patient stratification, enabling better use of clinical resources and improved patient outcomes.
- It should be understood that while embodiments described herein are described with respect to the cardiovascular assessment of patients confirmed as having or suspected of having COVID-19, such embodiments are not so limited. Embodiments may be applied for the cardiovascular assessment of patients confirmed as having or suspected of having any lung disease (e.g., other types of viral pneumonia (e.g., SARS (severe acute respiratory syndrome), MERS (Middle East respiratory syndrome), etc.), bacterial pneumonia, fungal pneumonia, mycoplasma pneumonia, and other types of pneumonia and other types of diseases).
-
Figure 1 shows aframework 100 for cardiovascular assessment of a patient confirmed as having or suspected of having a lung disease, in accordance with one or more embodiments.Figure 2 shows amethod 200 for cardiovascular assessment of a patient confirmed as having or suspected of having a lung disease, in accordance with one or more embodiments.Figure 1 andFigure 2 will be described together. The steps ofmethod 200 may be performed by one or more computing devices, such as, e.g.,computer 502 ofFigure 5 . - At
step 202, patient data of a patient is received. The patient may be confirmed as having or suspected of having a lung disease. In one embodiment, the lung disease is COVID-19. However, the lung disease may include any disease associated with the lungs of the patient, such as, e.g., other types of viral pneumonia (e.g., SARS (severe acute respiratory syndrome), MERS (Middle East respiratory syndrome), etc.), bacterial pneumonia, fungal pneumonia, mycoplasma pneumonia, and other types of pneumonia and other types of diseases. - In one embodiment, the patient data includes one or more input medical images of the chest (including the lungs and the heart) of the patient. The input medical images may depict abnormality patterns associated with the lung disease. For example, where the lung disease is COVID-19, the input medical images may show opacities such as, e.g., GGO (ground glass opacity), consolidation, crazy-paving pattern, atelectasis, interlobular septal thickening, pleural effusions, bronchiectasis, etc.
- In one embodiment, the input medical images are CT input medical images. For example, the input medical images may be
chest CT image 102 inframework 100 ofFigure 1 . However, the input medical images may be of any suitable modality, such as, e.g., MRI (magnetic resonance imaging), US (ultrasound), x-ray, or any other modality or combination of modalities. The input medical images may comprise one or more 2D images or 3D volumes. The input medical images may be received directly from an image acquisition device, such as, e.g., a CT scanner, as the input medical images are acquired, or can be received by loading previously acquired input medical images from a storage or memory of a computer system or receiving the input medical images from a remote computer system. - In one embodiment, the input medical images are acquired during a clinical workflow for diagnosing or treating the patient for the lung disease. Accordingly, the input medical images may be acquired with or without using a contrast agent, without cardiac gating, with a relatively lower spatial resolution as compared to typical cardiac CT imaging, and with low dose CT imaging. While such images are suitable for assessment of the lung disease, the images are relatively lower quality images as compared to typical medical images acquired for the purpose of assessing cardiovascular disease.
- In one embodiment, the patient data includes results of an assessment of the lung disease performed based on the input medical images. For example, the results of the assessment of the lung disease may be results of assessment of
lung disease 104 inframework 100 ofFigure 1 . In one embodiment, the assessment of the lung disease is a quantitative assessment of the lung disease performed on the input medical images using a machine learning based network. The results of the quantitative assessment may include metrics quantifying the lung disease. For example, where the lung disease is COVID-19, the quantitative assessment may quantify abnormality patterns associated with COVID-19. Exemplary metrics include a PO (percent of opacity) metric calculated as the total percent volume of the lungs that is affected by the disease and a LSS (lung severity score) metric calculated as a cumulative measure of the extent of lung involvement in the disease across each lobe of the lungs. Other metrics are also contemplated. In one embodiment, the assessment of the lung disease is a qualitative assessment of the lung disease performed by a clinician or other user. - In one embodiment, the patient data includes results of cardiovascular imaging exams. For example, the results of cardiovascular imaging exams may be results of
cardiovascular imaging exams 106 inframework 100 ofFigure 1 . The cardiovascular imaging exam may be based on any suitable modality or combination of modalities. Exemplary cardiovascular imaging exams include echocardiography, vascular ultrasound, cardiac MRI, cardiac CT, cardiac PET, or any other cardiovascular imaging exam. - In one embodiment, the patient data includes demographic and clinical data of the patient. For example, the demographic and clinical data may be demographic and
clinical data 108 inframework 100 ofFigure 1 . The demographic and clinical data may include any data relating to the patient, such as, e.g., age, gender, clinical history, genetic and family history, risk factors (e.g., hypertension, diabetes, etc.), lab values, etc. - In one embodiment, the demographic and clinical data includes sensor data of physiological measurements of the patient. The sensor data may include, e.g., ECG (electrocardiogram) data, EEG (electroencephalography) data, blood pressure data, O2 (oxygen) saturation, blood pH, glucose levels, etc. The sensor data may be acquired from sensors and medical equipment, including non-medical grade sensor devices. Exemplary sensors include a blood pressure meter, heart rate sensor, ECG monitor, pulse oximeter, O2 saturation sensor, sweat sensors, smart watches and wearable sensors, etc. The sensor data may be continuously acquired or periodically acquired at predetermined intervals.
- At
step 204, one or more cardiovascular risk scores are computed for the patient based on the patient data using a trained machine learning based network. The cardiovascular risk scores represent an assessment of risk or injury relating to the heart or vessels of the patient. In one example, cardiovascular risk scores 112 are computed using automated AI (artificial intelligence)-based cardiovasculardisease assessment system 110 inframework 100 ofFigure 1 . In one embodiment, the trained machine learning based network is a deep learning based network, however any other suitable machine learning based network may be employed. In one embodiment, the cardiovascular risk scores are based on multiple cardiovascular findings independently determined by different respective machine learning networks. The trained machine learning based network is trained to compute that cardiovascular risk scores during a prior offline or training stage using a training dataset and, once trained, applied atstep 204 during an online or inference stage. - In one embodiment, the cardiovascular risk scores of the patient represents a quantification of cardiovascular risk of the patient. For example, the cardiovascular risk scores may be a quantification of an amount of calcium in the coronary arteries (total calcium or calcium in each branch), a quantification of a calcium load in the aorta (e.g., the aortic root, thoracic aorta, or aortic valve leaflets), or a quantification of the size of the aorta and pulmonary artery. In another example, the cardiovascular risk scores may be a quantification of epicardial fat, paracardial fat, or epicardial adipose tissue. In another example, the cardiovascular risk scores may be a quantification of myocardial fat (infiltration).
- In one embodiment, a cardiovascular assessment of the patient is also determined based on the patient data using the trained machine learning based network. The cardiovascular assessment of the patient may comprise an automatic extraction of various anatomical structures (e.g., cardiovascular structures such as pericardium, heart chambers, aorta, pulmonary artery, etc.) from the input medical images. In one embodiment, the cardiovascular assessment of the patient comprises imaging biomarkers identified in the input medical images.
- In one embodiment, the cardiovascular assessment of the patient comprises cardiovascular-specific imaging features extracted from the input medical images by the trained machine learning based network. The extracted imaging features may be combined with other patient data for a more comprehensive assessment. For example, the extracted imaging features may be combined with cardiovascular disease imaging biomarkers obtained via ultrasound from other vascular territories, such as, e.g., carotids, aorta, and the ileo-femoral region.
- In one embodiment, the cardiovascular assessment of the patient comprises a recommended course of action for clinical decision support. For example, the recommended course of action may be a suggested duration for following up with the patient.
- In one embodiment, the cardiovascular risk scores for the patient comprises a combination metric representing an assessment of the cardiovascular disease of the patient, as well as the lung disease of the patient. The combination metric may be computed based on the imaging biomarkers in the input medical image combined with other patient data of the patient. In one example, the combination metric is an assessment of the overall cardiopulmonary system, including the lungs and the heart of the patient, representing the extent, severity, and risk of both the lung disease and cardiovascular disease. In another example, the combination metric may be the assessment of the lungs normalized in the context of the cardiovascular assessment (e.g., the quantification of the cardiovascular risk). In another example, the combination metric may represent the cardiovascular assessment (e.g., the quantification of the cardiovascular risk) quantified in the context of the assessment of the lung disease. For example, the quantification of the cardiovascular risk may be normalized with respect to an amount of infection in the lungs or a lung perfusion. Other metrics may also be employed that do not directly relate to cardiovascular disease.
- At
step 206, the cardiovascular risk scores and/or the cardiovascular assessment of the patient are output. For example, the cardiovascular risk scores and/or the cardiovascular assessment can be output by displaying the cardiovascular risk scores and/or the cardiovascular assessment on a display device of a computer system, storing the cardiovascular risk scores and/or the cardiovascular assessment on a memory or storage of a computer system, or by transmitting the cardiovascular risk scores and/or the cardiovascular assessment to a remote computer system. - In one embodiment, the cardiovascular risk scores and/or the cardiovascular assessment may be output as a visual report highlighting various sources of cardiac risk (e.g., coronary calcium, epicardial fat, enlargement of great vessels, etc.). The cardiovascular risk scores and/or the cardiovascular assessment for the patient may be displayed in the visual report along with cardiovascular risk scores and/or the cardiovascular assessments for other patients, where the patients are sorted (on demand or automatically) within the visual report based on cardiovascular risk. In one embodiment, a clinician (or other user) may be receive a notification (e.g., an email, text or chat message, or an application based notification) indicating that the cardiovascular risk scores and/or the cardiovascular assessment are complete. The clinical may interact with (e.g., select) the notification to view the cardiovascular risk scores and/or the cardiovascular assessment.
- In one embodiment, the cardiovascular risk scores and/or the cardiovascular assessment may be utilized by a clinical for patient management. For example, the clinician may order additional tests, change therapies, manage clinical resources, etc. based on the cardiovascular risk scores and/or the cardiovascular assessment.
- In one embodiment, the patient data (including both clinical and non-clinical sources of patient data) may be used in the context of the cardiovascular risk scores and/or the cardiovascular assessment to identify signs of cardiac distress. For example, the patient data may be sensor data from one or more sensors, such as an ECG monitor, blood pressure, sensor, O2 saturation sensor, smart watch, sweat sensor, laboratory testing data (e.g., troponin levels, blood glucose levels, cholesterol, etc.), or any other sensor. The sensor data, in combination with patient data, may be continuously received and used to build a continuously evolving model of the physiology of the patient. The model may be used to monitor the patient for sudden changes indicative of cardiac injury or stress based on the continuously received sensor data and the cardiovascular risk scores and/or the cardiovascular assessment. Where such indications of cardiac injury or stress are detected, a notification may be transmitted to the clinician for further assessment of the patient.
- Advantageously, the cardiovascular risk scores and/or the cardiovascular assessment of a patient in accordance with embodiments described herein assist clinicians in patient management decisions and patient stratification. The cardiovascular risk scores and/or the cardiovascular assessment are determined using patient data acquired in the clinical workflow for diagnosing or treating the lung disease and therefore requires minimal time from clinicians, which is particularly important for clinicians treating patients with COVID-19. Further, the cardiovascular risk scores and/or the cardiovascular assessment is determined based on a combination of various patient data and thus, the accuracy of specific patient data is not critical for determining the cardiovascular assessment.
- Embodiments described herein are described with respect to the claimed systems as well as with respect to the claimed methods. Features, advantages or alternative embodiments herein can be assigned to the other claimed objects and vice versa. In other words, claims for the systems can be improved with features described or claimed in the context of the methods. In this case, the functional features of the method are embodied by objective units of the providing system.
- Furthermore, embodiments described herein are described with respect to methods and systems for cardiovascular assessment of patients suspected of having COVID-19 using a trained machine learning based network, as well as with respect to methods and systems for training a machine learning based network for cardiovascular assessment of patients suspected of having COVID-19. Features, advantages or alternative embodiments herein can be assigned to the other claimed objects and vice versa. In other words, claims for methods and systems for training a machine learning based generator network can be improved with features described or claimed in context of the methods and systems for utilizing a trained machine learning based generator network, and vice versa.
- In particular, the trained machine learning based network of the methods and systems for cardiovascular assessment of patients suspected of having COVID-19 can be adapted by the methods and systems for training the machine learning based network for cardiovascular assessment of patients suspected of having COVID-19. Furthermore, the input data of the trained machine learning based network can comprise advantageous features and embodiments of the training input data, and vice versa. Furthermore, the output data of the trained machine learning based network can comprise advantageous features and embodiments of the output training data, and vice versa.
- In general, a trained machine learning based network mimics cognitive functions that humans associate with other human minds. In particular, by training based on training data, the trained machine learning based network is able to adapt to new circumstances and to detect and extrapolate patterns.
- In general, parameters of a machine learning based network can be adapted by means of training. In particular, supervised training, semi-supervised training, unsupervised training, reinforcement learning and/or active learning can be used. Furthermore, representation learning (an alternative term is "feature learning") can be used. In particular, the parameters of the trained machine learning based network can be adapted iteratively by several steps of training.
- In particular, a trained machine learning based network can comprise a neural network, a support vector machine, a decision tree, and/or a Bayesian network, and/or the trained machine learning based network can be based on k-means clustering, Q-learning, genetic algorithms, and/or association rules. In particular, a neural network can be a deep neural network, a convolutional neural network, or a convolutional deep neural network. Furthermore, a neural network can be an adversarial network, a deep adversarial network and/or a generative adversarial network.
-
Figure 3 shows an embodiment of an artificialneural network 300, in accordance with one or more embodiments. Alternative terms for "artificial neural network" are "neural network", "artificial neural net" or "neural net". Machine learning networks described herein, such as, e.g., the automated AI-based cardiovasculardisease assessment system 110 ofFigure 1 and the machine learning based network applied atstep 204 ofFigure 2 , may be implemented using artificialneural network 300. - The artificial
neural network 300 comprises nodes 302-322 andedges edge Figure 3 , theedge 332 is a directed connection from thenode 302 to thenode 306, and theedge 334 is a directed connection from thenode 304 to thenode 306. Anedge - In this embodiment, the nodes 302-322 of the artificial
neural network 300 can be arranged in layers 324-330, wherein the layers can comprise an intrinsic order introduced by theedges Figure 3 , there is aninput layer 324 comprisingonly nodes output layer 330 comprisingonly node 322 without outgoing edges, andhidden layers input layer 324 and theoutput layer 330. In general, the number ofhidden layers nodes input layer 324 usually relates to the number of input values of theneural network 300, and the number ofnodes 322 within theoutput layer 330 usually relates to the number of output values of theneural network 300. - In particular, a (real) number can be assigned as a value to every node 302-322 of the
neural network 300. Here, x(n) i denotes the value of the i-th node 302-322 of the n-th layer 324-330. The values of the nodes 302-322 of theinput layer 324 are equivalent to the input values of theneural network 300, the value of thenode 322 of theoutput layer 330 is equivalent to the output value of theneural network 300. Furthermore, eachedge -
- Herein, the function f is a transfer function (another term is "activation function"). Known transfer functions are step functions, sigmoid function (e.g. the logistic function, the generalized logistic function, the hyperbolic tangent, the Arctangent function, the error function, the smoothstep function) or rectifier functions The transfer function is mainly used for normalization purposes.
- In particular, the values are propagated layer-wise through the neural network, wherein values of the
input layer 324 are given by the input of theneural network 300, wherein values of the firsthidden layer 326 can be calculated based on the values of theinput layer 324 of the neural network, wherein values of the secondhidden layer 328 can be calculated based in the values of the firsthidden layer 326, etc. - In order to set the values w(m,n) i,j for the edges, the
neural network 300 has to be trained using training data. In particular, training data comprises training input data and training output data (denoted as ti). For a training step, theneural network 300 is applied to the training input data to generate calculated output data. In particular, the training data and the calculated output data comprise a number of values, said number being equal with the number of nodes of the output layer. -
- wherein Y is a learning rate, and the numbers δ(n) j can be recursively calculated as
output layer 330, wherein f is the first derivative of the activation function, and y(n+1) j is the comparison training value for the j-th node of theoutput layer 330. -
Figure 4 shows a convolutionalneural network 400, in accordance with one or more embodiments. Machine learning networks described herein, such as, e.g., the automated AI-based cardiovasculardisease assessment system 110 ofFigure 1 and the machine learning based network applied atstep 204 ofFigure 2 , may be implemented using convolutionalneural network 400. - In the embodiment shown in
Figure 4 , the convolutional neural network comprises 400 aninput layer 402, aconvolutional layer 404, apooling layer 406, a fully connectedlayer 408, and anoutput layer 410. Alternatively, the convolutionalneural network 400 can comprise severalconvolutional layers 404, several poolinglayers 406, and several fullyconnected layers 408, as well as other types of layers. The order of the layers can be chosen arbitrarily, usually fullyconnected layers 408 are used as the last layers before theoutput layer 410. - In particular, within a convolutional
neural network 400, the nodes 412-420 of one layer 402-410 can be considered to be arranged as a d-dimensional matrix or as a d-dimensional image. In particular, in the two-dimensional case the value of the node 412-420 indexed with i and j in the n-th layer 402-410 can be denoted as x(n)[i,j]. However, the arrangement of the nodes 412-420 of one layer 402-410 does not have an effect on the calculations executed within the convolutionalneural network 400 as such, since these are given solely by the structure and the weights of the edges. - In particular, a
convolutional layer 404 is characterized by the structure and the weights of the incoming edges forming a convolution operation based on a certain number of kernels. In particular, the structure and the weights of the incoming edges are chosen such that the values x(n) k of thenodes 414 of theconvolutional layer 404 are calculated as a convolution x(n) k = Kk * x(n-1) based on the values x(n-1) of thenodes 412 of thepreceding layer 402, where the convolution * is defined in the two-dimensional case as - Here the k-th kernel Kk is a d-dimensional matrix (in this embodiment a two-dimensional matrix), which is usually small compared to the number of nodes 412-418 (e.g. a 3x3 matrix, or a 5x5 matrix). In particular, this implies that the weights of the incoming edges are not independent, but chosen such that they produce said convolution equation. In particular, for a kernel being a 3x3 matrix, there are only 9 independent weights (each entry of the kernel matrix corresponding to one independent weight), irrespectively of the number of nodes 412-420 in the respective layer 402-410. In particular, for a
convolutional layer 404, the number ofnodes 414 in the convolutional layer is equivalent to the number ofnodes 412 in thepreceding layer 402 multiplied with the number of kernels. - If the
nodes 412 of thepreceding layer 402 are arranged as a d-dimensional matrix, using a plurality of kernels can be interpreted as adding a further dimension (denoted as "depth" dimension), so that thenodes 414 of theconvolutional layer 414 are arranged as a (d+1)-dimensional matrix. If thenodes 412 of thepreceding layer 402 are already arranged as a (d+1)-dimensional matrix comprising a depth dimension, using a plurality of kernels can be interpreted as expanding along the depth dimension, so that thenodes 414 of theconvolutional layer 404 are arranged also as a (d+1)-dimensional matrix, wherein the size of the (d+1)-dimensional matrix with respect to the depth dimension is by a factor of the number of kernels larger than in thepreceding layer 402. - The advantage of using
convolutional layers 404 is that spatially local correlation of the input data can exploited by enforcing a local connectivity pattern between nodes of adjacent layers, in particular by each node being connected to only a small region of the nodes of the preceding layer. - In embodiment shown in
Figure 4 , theinput layer 402 comprises 36nodes 412, arranged as a two-dimensional 6x6 matrix. Theconvolutional layer 404 comprises 72nodes 414, arranged as two two-dimensional 6x6 matrices, each of the two matrices being the result of a convolution of the values of the input layer with a kernel. Equivalently, thenodes 414 of theconvolutional layer 404 can be interpreted as arranges as a three-dimensional 6x6x2 matrix, wherein the last dimension is the depth dimension. - A
pooling layer 406 can be characterized by the structure and the weights of the incoming edges and the activation function of itsnodes 416 forming a pooling operation based on a non-linear pooling function f. For example, in the two dimensional case the values x(n) of thenodes 416 of thepooling layer 406 can be calculated based on the values x(n-1) of thenodes 414 of thepreceding layer 404 as - In other words, by using a
pooling layer 406, the number ofnodes nodes 414 in thepreceding layer 404 with asingle node 416 being calculated as a function of the values of said number of neighboring nodes in the pooling layer. In particular, the pooling function f can be the max-function, the average or the L2-Norm. In particular, for apooling layer 406 the weights of the incoming edges are fixed and are not modified by training. - The advantage of using a
pooling layer 406 is that the number ofnodes - In the embodiment shown in
Figure 4 , thepooling layer 406 is a max-pooling, replacing four neighboring nodes with only one node, the value being the maximum of the values of the four neighboring nodes. The max-pooling is applied to each d-dimensional matrix of the previous layer; in this embodiment, the max-pooling is applied to each of the two two-dimensional matrices, reducing the number of nodes from 72 to 18. - A fully-connected
layer 408 can be characterized by the fact that a majority, in particular, all edges betweennodes 416 of theprevious layer 406 and thenodes 418 of the fully-connectedlayer 408 are present, and wherein the weight of each of the edges can be adjusted individually. - In this embodiment, the
nodes 416 of thepreceding layer 406 of the fully-connectedlayer 408 are displayed both as two-dimensional matrices, and additionally as non-related nodes (indicated as a line of nodes, wherein the number of nodes was reduced for a better presentability). In this embodiment, the number ofnodes 418 in the fully connectedlayer 408 is equal to the number ofnodes 416 in thepreceding layer 406. Alternatively, the number ofnodes - Furthermore, in this embodiment, the values of the
nodes 420 of theoutput layer 410 are determined by applying the Softmax function onto the values of thenodes 418 of thepreceding layer 408. By applying the Softmax function, the sum the values of allnodes 420 of theoutput layer 410 is 1, and all values of allnodes 420 of the output layer are real numbers between 0 and 1. - A convolutional
neural network 400 can also comprise a ReLU (rectified linear units) layer. In particular, the number of nodes and the structure of the nodes contained in a ReLU layer is equivalent to the number of nodes and the structure of the nodes contained in the preceding layer. In particular, the value of each node in the ReLU layer is calculated by applying a rectifying function to the value of the corresponding node of the preceding layer. Examples for rectifying functions are f(x) = max(0,x), the tangent hyperbolics function or the sigmoid function. - In particular, convolutional
neural networks 400 can be trained based on the backpropagation algorithm. For preventing overfitting, methods of regularization can be used, e.g. dropout of nodes 412-420, stochastic pooling, use of artificial data, weight decay based on the L1 or the L2 norm, or max norm constraints. - Systems, apparatuses, and methods described herein may be implemented using digital circuitry, or using one or more computers using well-known computer processors, memory units, storage devices, computer software, and other components. Typically, a computer includes a processor for executing instructions and one or more memories for storing instructions and data. A computer may also include, or be coupled to, one or more mass storage devices, such as one or more magnetic disks, internal hard disks and removable disks, magneto-optical disks, optical disks, etc.
- Systems, apparatus, and methods described herein may be implemented using computers operating in a client-server relationship. Typically, in such a system, the client computers are located remotely from the server computer and interact via a network. The client-server relationship may be defined and controlled by computer programs running on the respective client and server computers.
- Systems, apparatus, and methods described herein may be implemented within a network-based cloud computing system. In such a network-based cloud computing system, a server or another processor that is connected to a network communicates with one or more client computers via a network. A client computer may communicate with the server via a network browser application residing and operating on the client computer, for example. A client computer may store data on the server and access the data via the network. A client computer may transmit requests for data, or requests for online services, to the server via the network. The server may perform requested services and provide data to the client computer(s). The server may also transmit data adapted to cause a client computer to perform a specified function, e.g., to perform a calculation, to display specified data on a screen, etc. For example, the server may transmit a request adapted to cause a client computer to perform one or more of the steps or functions of the methods and workflows described herein, including one or more of the steps or functions of
Figures 1-2 . Certain steps or functions of the methods and workflows described herein, including one or more of the steps or functions ofFigures 1-2 , may be performed by a server or by another processor in a network-based cloud-computing system. Certain steps or functions of the methods and workflows described herein, including one or more of the steps ofFigures 1-2 , may be performed by a client computer in a network-based cloud computing system. The steps or functions of the methods and workflows described herein, including one or more of the steps ofFigures 1-2 , may be performed by a server and/or by a client computer in a network-based cloud computing system, in any combination. - Systems, apparatus, and methods described herein may be implemented using a computer program product tangibly embodied in an information carrier, e.g., in a non-transitory machine-readable storage device, for execution by a programmable processor; and the method and workflow steps described herein, including one or more of the steps or functions of
Figures 1-2 , may be implemented using one or more computer programs that are executable by such a processor. A computer program is a set of computer program instructions that can be used, directly or indirectly, in a computer to perform a certain activity or bring about a certain result. A computer program can be written in any form of programming language, including compiled or interpreted languages, and it can be deployed in any form, including as a stand-alone program or as a module, component, subroutine, or other unit suitable for use in a computing environment. - A high-level block diagram of an
example computer 502 that may be used to implement systems, apparatus, and methods described herein is depicted inFigure 5 .Computer 502 includes aprocessor 504 operatively coupled to adata storage device 512 and amemory 510.Processor 504 controls the overall operation ofcomputer 502 by executing computer program instructions that define such operations. The computer program instructions may be stored indata storage device 512, or other computer readable medium, and loaded intomemory 510 when execution of the computer program instructions is desired. Thus, the method and workflow steps or functions ofFigures 1-2 can be defined by the computer program instructions stored inmemory 510 and/ordata storage device 512 and controlled byprocessor 504 executing the computer program instructions. For example, the computer program instructions can be implemented as computer executable code programmed by one skilled in the art to perform the method and workflow steps or functions ofFigures 1-2 . Accordingly, by executing the computer program instructions, theprocessor 504 executes the method and workflow steps or functions ofFigures 1-2 .Computer 502 may also include one or more network interfaces 506 for communicating with other devices via a network.Computer 502 may also include one or more input/output devices 508 that enable user interaction with computer 502 (e.g., display, keyboard, mouse, speakers, buttons, etc.). -
Processor 504 may include both general and special purpose microprocessors, and may be the sole processor or one of multiple processors ofcomputer 502.Processor 504 may include one or more central processing units (CPUs), for example.Processor 504,data storage device 512, and/ormemory 510 may include, be supplemented by, or incorporated in, one or more application-specific integrated circuits (ASICs) and/or one or more field programmable gate arrays (FPGAs). -
Data storage device 512 andmemory 510 each include a tangible non-transitory computer readable storage medium.Data storage device 512, andmemory 510, may each include high-speed random access memory, such as dynamic random access memory (DRAM), static random access memory (SRAM), double data rate synchronous dynamic random access memory (DDR RAM), or other random access solid state memory devices, and may include non-volatile memory, such as one or more magnetic disk storage devices such as internal hard disks and removable disks, magneto-optical disk storage devices, optical disk storage devices, flash memory devices, semiconductor memory devices, such as erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM), digital versatile disc read-only memory (DVD-ROM) disks, or other non-volatile solid state storage devices. - Input/
output devices 508 may include peripherals, such as a printer, scanner, display screen, etc. For example, input/output devices 508 may include a display device such as a cathode ray tube (CRT) or liquid crystal display (LCD) monitor for displaying information to the user, a keyboard, and a pointing device such as a mouse or a trackball by which the user can provide input tocomputer 502. - An
image acquisition device 514 can be connected to thecomputer 502 to input image data (e.g., medical images) to thecomputer 502. It is possible to implement theimage acquisition device 514 and thecomputer 502 as one device. It is also possible that theimage acquisition device 514 and thecomputer 502 communicate wirelessly through a network. In a possible embodiment, thecomputer 502 can be located remotely with respect to theimage acquisition device 514. - Any or all of the systems and apparatus discussed herein, including automated AI-based cardiovascular
disease assessment system 110 ofFigure 1 , the machine learning based network applied atstep 204 ofFigure 2 , the artificialneural network 300 ofFigure 3 , and the convolutionalneural network 400 ofFigure 4 , may be implemented using one or more computers such ascomputer 502. - One skilled in the art will recognize that an implementation of an actual computer or computer system may have other structures and may contain other components as well, and that
Figure 5 is a high level representation of some of the components of such a computer for illustrative purposes. - The foregoing Detailed Description is to be understood as being in every respect illustrative and exemplary, but not restrictive, and the scope of the invention disclosed herein is not to be determined from the Detailed Description, but rather from the claims as interpreted according to the full breadth permitted by the patent laws. It is to be understood that the embodiments shown and described herein are only illustrative of the principles of the present invention and that various modifications may be implemented by those skilled in the art without departing from the scope and spirit of the invention. Those skilled in the art could implement various other feature combinations without departing from the scope and spirit of the invention.
Claims (15)
- A computer implemented method comprising:receiving (202) patient data of a patient, the patient data comprising one or more input medical images of a chest of the patient and results of an assessment of a lung disease performed based on the one or more input medical images; andcomputing (204) one or more cardiovascular risk scores for the patient based on the patient data using a trained machine learning based network.
- The computer implemented method of claim 1, wherein the lung disease is COVID-19 (coronavirus disease 2019).
- The computer implemented method of claim 1 or 2, wherein the one or more input medical images was acquired without a contrast agent and/or without cardiac gating.
- The computer implemented method of any one of claims 1 - 3, wherein computing one or more cardiovascular risk scores for the patient based on the patient data using a trained machine learning based network comprises:
determining a metric representing an assessment of a cardiovascular disease and the assessment of the lung disease. - The computer implemented method of any one of claims 1 - 4, wherein the patient data further comprises sensor data of physiological measurements of the patient, the method further comprising:continuously receiving the sensor data; andmonitoring the patient based on the continuously received sensor data and the one or more cardiovascular risk scores.
- The computer implemented method of any one of claims 1 - 5, wherein the patient data further comprises at least one of demographic and clinical data of the patient and cardiovascular imaging exams of the patient.
- The computer implemented method of any one of claims 1 - 6, wherein the lung disease is a viral pneumonia.
- The computer implemented method of any one of claims 1 - 7, further comprising:
generating medical images of the chest of the patient using a CT imaging device. - The computer implemented method of any one of claims 1 - 8, further comprising at least one of the steps of:displaying the computed cardiovascular risk scores;outputting the computed cardiovascular risk scores in a computer readable form;selecting, from a list of therapeutical options for the patient, at least one therapeutical option as a function of the computed cardiovascular risk scores, and outputting the selected option; andmanaging the patient based on the one or more cardiovascular risk scores.
- The computer implemented method of any one of claims 1 - 9, further comprising:
training the machine learning based network based on prior patient data. - An apparatus comprising:means for receiving (202) patient data of a patient, the patient data comprising one or more input medical images of a chest of the patient and results of an assessment of a lung disease performed based on the one or more input medical images; andmeans for computing (204) one or more cardiovascular risk scores for the patient based on the patient data using a trained machine learning based network.
- The apparatus of claim 11, wherein the means for receiving (202) and/or the means for computing (204) is implemented to execute the method of any one of claims 1 - 10.
- The apparatus of claim 11 or 12, further comprising a CT imaging device for providing medical images of the chest of the patient.
- A non-transitory computer readable medium storing computer program instructions, the computer program instructions when executed by a processor cause the processor to perform operations comprising:receiving (202) patient data of a patient, the patient data comprising one or more input medical images of a chest of the patient and results of an assessment of a lung disease performed based on the one or more input medical images; andcomputing (204) one or more cardiovascular risk scores for the patient based on the patient data using a trained machine learning based network.
- The non-transitory computer readable medium of claim 11, wherein the computer program instructions cause the processor to perform operations and/or method steps to execute the method of any one of claims 1 - 10.
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US202063009517P | 2020-04-14 | 2020-04-14 | |
US16/877,646 US20210319900A1 (en) | 2020-04-14 | 2020-05-19 | Cardiovascular assessment of patients suspected of having covid-19 |
Publications (1)
Publication Number | Publication Date |
---|---|
EP3896702A1 true EP3896702A1 (en) | 2021-10-20 |
Family
ID=75539055
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
EP21167781.0A Pending EP3896702A1 (en) | 2020-04-14 | 2021-04-12 | Cardiovascular assessment of patients suspected of having covid-19 |
Country Status (3)
Country | Link |
---|---|
US (1) | US20210319900A1 (en) |
EP (1) | EP3896702A1 (en) |
CN (1) | CN113538327A (en) |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113940640B (en) * | 2021-11-12 | 2023-04-18 | 清华大学 | Cardiovascular disease risk control method, system and storage medium |
RU2767624C1 (en) * | 2021-12-08 | 2022-03-18 | Федеральное государственное бюджетное образовательное учреждение высшего образования "Национальный исследовательский Мордовский государственный университет им. Н.П. Огарёва" | Method for determining the risk of developing cardiovascular complications in patients with stage ii essential arterial hypertension within 12 months after covid-19 |
Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP3404667A1 (en) * | 2017-05-19 | 2018-11-21 | Siemens Healthcare GmbH | Learning based methods for personalized assessment, long-term prediction and management of atherosclerosis |
Family Cites Families (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2007038787A1 (en) * | 2005-09-29 | 2007-04-05 | General Hospital Corporation | Method and apparatus for optical imaging via spectral encoding |
US20110202486A1 (en) * | 2009-07-21 | 2011-08-18 | Glenn Fung | Healthcare Information Technology System for Predicting Development of Cardiovascular Conditions |
CN102713979A (en) * | 2009-12-21 | 2012-10-03 | 皇家飞利浦电子股份有限公司 | Processing an image dataset based on clinically categorized populations |
BR112015023722A2 (en) * | 2013-03-18 | 2017-07-18 | Koninklijke Philips Nv | system configured to monitor individuals who are chronic obstructive pulmonary disease patients, and method configured to monitor individuals who are chronic obstructive pulmonary disease patients |
US10706592B2 (en) * | 2014-01-06 | 2020-07-07 | Cedars-Sinai Medical Center | Systems and methods for myocardial perfusion MRI without the need for ECG gating and additional systems and methods for improved cardiac imaging |
EP3404666A3 (en) * | 2017-04-28 | 2019-01-23 | Siemens Healthcare GmbH | Rapid assessment and outcome analysis for medical patients |
US10825167B2 (en) * | 2017-04-28 | 2020-11-03 | Siemens Healthcare Gmbh | Rapid assessment and outcome analysis for medical patients |
EP3564963A1 (en) * | 2018-05-02 | 2019-11-06 | Siemens Healthcare GmbH | System and methods for fast computation of computed tomography based fractional flow reserve |
MX2021013663A (en) * | 2019-05-10 | 2022-01-24 | Locus Ip Co Llc | Compositions and methods for treating biofilm-related lung conditions. |
US20210287795A1 (en) * | 2020-03-12 | 2021-09-16 | Optellum Limited | Cad device and method for assisting an estimation of lung disease from medical images |
-
2020
- 2020-05-19 US US16/877,646 patent/US20210319900A1/en active Pending
-
2021
- 2021-04-12 EP EP21167781.0A patent/EP3896702A1/en active Pending
- 2021-04-14 CN CN202110399154.2A patent/CN113538327A/en active Pending
Patent Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP3404667A1 (en) * | 2017-05-19 | 2018-11-21 | Siemens Healthcare GmbH | Learning based methods for personalized assessment, long-term prediction and management of atherosclerosis |
Non-Patent Citations (1)
Title |
---|
DE VOS BOB D ET AL: "Automatic machine learning based prediction of cardiovascular events in lung cancer screening data", PROGRESS IN BIOMEDICAL OPTICS AND IMAGING, SPIE - INTERNATIONAL SOCIETY FOR OPTICAL ENGINEERING, BELLINGHAM, WA, US, vol. 9414, 20 March 2015 (2015-03-20), pages 94140D - 94140D, XP060052102, ISSN: 1605-7422, ISBN: 978-1-5106-0027-0, DOI: 10.1117/12.2082242 * |
Also Published As
Publication number | Publication date |
---|---|
US20210319900A1 (en) | 2021-10-14 |
CN113538327A (en) | 2021-10-22 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Tekkeşin | Artificial intelligence in healthcare: past, present and future | |
US11864944B2 (en) | Systems and methods for a deep neural network to enhance prediction of patient endpoints using videos of the heart | |
US11728039B2 (en) | Methods and systems for predicting sensitivity of blood flow calculations to changes in anatomical geometry | |
US10192640B2 (en) | Fractional flow reserve decision support system | |
US11342080B2 (en) | Method and system for disease progression modeling and therapy optimizing for individual patients | |
US20180315505A1 (en) | Optimization of clinical decision making | |
Lim et al. | Artificial intelligence in cardiovascular imaging | |
EP3905257A1 (en) | Risk prediction for covid-19 patient management | |
EP3896702A1 (en) | Cardiovascular assessment of patients suspected of having covid-19 | |
US12002583B2 (en) | Universal health machine for the automatic assessment of patients | |
Lin et al. | Echocardiography-based AI detection of regional wall motion abnormalities and quantification of cardiac function in myocardial infarction | |
EP4057296A1 (en) | Machine learning for automatic detection of intracranial hemorrhages with uncertainty measures from ct images | |
US11678853B2 (en) | Multi-task learning framework for fully automated assessment of coronary artery disease | |
US11847779B2 (en) | Clinical decision support for cardiovascular disease based on a plurality of medical assessments | |
US11615529B2 (en) | Automatic, dynamic, and adaptive slice planning for cardiac MRI acquisition | |
US20230071558A1 (en) | Fully automated assessment of coronary vulnerable plaque in coronary ct images using radiomic features | |
US11861828B2 (en) | Automated estimation of midline shift in brain ct images | |
EP4261841A1 (en) | Cardio ai smart assistant for semantic image analysis of medical imaging studies | |
US20240046453A1 (en) | Semi-supervised learning leveraging cross-domain data for medical imaging analysis | |
US20240104719A1 (en) | Multi-task learning framework for fully automated assessment of coronary arteries in angiography images | |
Reddy et al. | Enhanced Pre-Processing Based Cardiac Valve Block Detection Using Deep Learning Architectures | |
KR20240008030A (en) | Method for providing information on prediction of cardiac function and device using the same | |
CN117523332A (en) | Model training method, model training system, method, device and storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PUAI | Public reference made under article 153(3) epc to a published international application that has entered the european phase |
Free format text: ORIGINAL CODE: 0009012 |
|
STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: REQUEST FOR EXAMINATION WAS MADE |
|
17P | Request for examination filed |
Effective date: 20210412 |
|
AK | Designated contracting states |
Kind code of ref document: A1 Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR |
|
B565 | Issuance of search results under rule 164(2) epc |
Effective date: 20210827 |
|
RBV | Designated contracting states (corrected) |
Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR |
|
RAP1 | Party data changed (applicant data changed or rights of an application transferred) |
Owner name: SIEMENS HEALTHINEERS AG |
|
STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: EXAMINATION IS IN PROGRESS |
|
17Q | First examination report despatched |
Effective date: 20240801 |